Related papers: Creative Invention Benchmark
We present a system for identifying conceptual shifts between visual categories, which will form the basis for a co-creative drawing system to help users draw more creative sketches. The system recognizes human sketches and matches them to…
Despite the increasing use of large language models for creative tasks, their outputs often lack diversity. Common solutions, such as sampling at higher temperatures, can compromise the quality of the results. Dealing with this trade-off is…
Robust discrete optimization is a highly active field of research where a plenitude of combinations between decision criteria, uncertainty sets and underlying nominal problems are considered. Usually, a robust problem becomes harder to…
The metaverse, enormous virtual-physical cyberspace, has brought unprecedented opportunities for artists to blend every corner of our physical surroundings with digital creativity. This article conducts a comprehensive survey on…
Despite popular media interest in uncovering the creative habits of successful people, there is a surprising paucity of empirical research on the diversity of tendencies and preferences people have when engaged in creative work. We…
The accelerating pace of scientific publication makes it difficult to identify truly original research among incremental work. We propose a framework for estimating the conceptual novelty of research papers by combining semantic…
The field of High-Performance Computing (HPC) is defined by providing computing devices with highest performance for a variety of demanding scientific users. The tight co-design relationship between HPC providers and users propels the field…
Increasingly, large language models (LLMs) are being used to automate workplace processes requiring a high degree of creativity. While much prior work has examined the creativity of LLMs, there has been little research on whether they can…
We argue for the need for a new generation of data science solutions that can democratize recent advances in data engineering and artificial intelligence for non-technical users from various disciplines, enabling them to unlock the full…
Designing system algorithms remains challenging, where the discontinuous nature of the solution space often forces system engineers to rely on generic heuristics at the expense of performance. We study whether LLMs can practically drive…
Large language models (LLMs) have manifested strong ability to generate codes for productive activities. However, current benchmarks for code synthesis, such as HumanEval, MBPP, and DS-1000, are predominantly oriented towards introductory…
Interactive intelligent systems, i.e., interactive systems that employ AI technologies, are currently present in many parts of our social, public and political life. An issue reoccurring often in the development of these systems is the…
Evaluating how Large Language Models (LLMs) handle complex, specialized knowledge remains a critical challenge. We address this through the lens of climate change by introducing CLINB, a benchmark that assesses models on open-ended,…
AI agents have the potential to aid users on a variety of consequential tasks, including conducting scientific research. To spur the development of useful agents, we need benchmarks that are challenging, but more crucially, directly…
In this paper, we propose a spatially constrained clustering problem belonging to the family of "p-regions" problems. Our formulation is motivated by the recent developments of economic complexity on the evolution of the economic output…
While programming is one of the most broadly applicable skills in modern society, modern machine learning models still cannot code solutions to basic problems. Despite its importance, there has been surprisingly little work on evaluating…
Product innovation assessment in software sector is a timely topic. Nevertheless, research on that subject is particularly scant. As a result, there is a lack of criteria to measure software innovativeness. In a context of theoretical and…
Scientists have demonstrated that quantum computing has presented novel approaches to address computational challenges, each varying in complexity. Adapting problem-solving strategies is crucial to harness the full potential of quantum…
We introduce DS-1000, a code generation benchmark with a thousand data science problems spanning seven Python libraries, such as NumPy and Pandas. Compared to prior works, DS-1000 incorporates three core features. First, our problems…
Context. Innovation is promoted in companies to help them stay competitive. Four types of innovation are defined: product, process, business, and organizational. Objective. We want to understand the perception of the innovation concept in…